MiroThinker icon
MiroThinker icon

MiroThinker

MiroThinker is an open-source search agent model, built for tool-augmented reasoning and real-world information seeking, aiming to match the deep research experience of OpenAI Deep Research and Gemini Deep Research.

MiroThinker screenshot 1

Cost / License

  • Free
  • Open Source (MIT)

Platforms

  • Python
  • Windows
  • Linux
  • Mac
  • Self-Hosted
-
No reviews
1like
0comments
0news articles

Features

Suggest and vote on features
  1.  Agentic AI
  2.  AI Chatbot
  3.  AI-Powered

 Tags

MiroThinker News & Activities

Highlights All activities

Recent activities

Show all activities

MiroThinker information

  • Developed by

    SG flagMiroMind
  • Licensing

    Open Source (MIT) and Free product.
  • Written in

  • Alternatives

    51 alternatives listed
  • Supported Languages

    • English

AlternativeTo Category

AI Tools & Services

GitHub repository

  •  4,066 Stars
  •  256 Forks
  •  11 Open Issues
  •   Updated  
View on GitHub
MiroThinker was added to AlternativeTo by Paul on and this page was last updated .
No comments or reviews, maybe you want to be first?
Post comment/review

Featured in Lists

LLMs that can be used for free without limits

List by Akshith Anoop with 14 apps, updated

What is MiroThinker?

MiroThinker is MiroMind's Flagship Research Agent Model. It is an open-source search model designed to advance tool-augmented reasoning and information-seeking capabilities, enabling complex real-world research workflows across diverse challenges.

The project currently comprises four key components:

  • MiroThinker: An open-source search model that natively supports tool-assisted reasoning, achieving leading performance across multiple benchmarks (e.g., HLE, HLE-Text-2158, HLE-Text-500, BrowseComp, BrowseComp-ZH, GAIA, XBench-DeepSearch, FutureX, and Frames). See Quick Start.
  • MiroFlow: An open-source research agent framework that offers reproducible state-of-the-art performance across multiple benchmarks. See MiroFlow for details.
  • MiroVerse: A premium open-source training dataset with 147k samples supporting research agent training. See MiroVerse on HuggingFace.
  • MiroTrain / MiroRL: Training infrastructure that supports stable and efficient training for research agent models. See MiroTrain and MiroRL for details.

Official Links